© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 94053
    Prev
    Next
    INDEX
    Explanations

    ip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commencement
    -0.06
    تمر
    -0.06
     Norwich
    -0.06
    vanished
    -0.06
     smuggling
    -0.06
     nh
    -0.06
     augmentation
    -0.06
     공동
    -0.06
    xEC
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ip
    0.12
     recip
    0.10
    cip
    0.10
    IP
    0.09
    цип
    0.09
    zip
    0.08
    ipp
    0.07
    ipt
    0.07
    pip
    0.07
     anticip
    0.07
    Activations Density 0.008%

    No Known Activations